10.18453/rosdok_id00001865
Mohammed, Redwan Abdo Abdullah
Redwan Abdo Abdullah
Mohammed
http://d-nb.info/gnd/112675353X
Predicting human behavior in smart environments
Universität Rostock
2017
004 Data processing Computer sciences
2017
en
http://purl.uni-rostock.de/rosdok/id00001865
urn:nbn:de:gbv:28-diss2017-0029-6
Predicting human behavior is desirable in many application scenarios in smart environments. The existing models for eye movements do not take contextual factors into account. This addressed in this thesis using a systematic machine-learning approach, where user profiles for eye movements behaviors are learned from data. In addition, a theoretical innovation is presented, which goes beyond pure data analysis. The thesis proposed the modeling of eye movements as a Markov Decision Processes. It uses Inverse Reinforcement Learning paradigm to infer the user eye movements behaviors.